© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36132
    Prev
    Next
    INDEX
    Explanations

    scientific study comparison

    np_acts-logits-general · gemini-2.5-flash-lite

    the main thing this neuron does is find numeric tokens (numbers and measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    の一つ
    -1.01
     ͡°
    -0.92
     Geset
    -0.92
    both
    -0.91
     tampilan
    -0.91
     both
    -0.91
    广泛
    -0.90
     ikiwa
    -0.90
    ilarities
    -0.90
    omalies
    -0.90
    POSITIVE LOGITS
    “
    1.13
    </h4>
    1.00
     souhaite
    0.97
    於
    0.95
     огромное
    0.93
    GRAFIA
    0.93
    -
    0.91
     российский
    0.91
    trou
    0.90
     ”
    0.90
    Activations Density 0.170%

    No Known Activations